CS223B Homework 1 Results. Considered 2 Metrics Raw score –Number of pixels in error Weighted...

17
CS223B Homework 1 Results
  • date post

    21-Dec-2015
  • Category

    Documents

  • view

    215
  • download

    0

Transcript of CS223B Homework 1 Results. Considered 2 Metrics Raw score –Number of pixels in error Weighted...

CS223BHomework 1 Results

Considered 2 Metrics

• Raw score– Number of pixels in error

• Weighted score– Car pixels weighted more heavily than non-car pixels– Range from 50-100– Formula:

40 * (% of correct car pixels)+ 30 * (1.0 - % of false positive pixels)+ 20 * (% of correct non-car pixels)+ 10 * (1.0 - % of false negative pixels)

Group Performance (Based on Error Pixels)

0

1

2

3

4

5

6

7

3000 4000 5000 6000 7000 8000 9000 10000 11000 12000 13000 14000 15000 16000

Average Error Pixels

Nu

mb

er o

f G

rou

ps

Group Performance (Based on Weighted Score)

0

2

4

6

8

10

12

14

60 65 70 75 80 85 90 95

Weighted Score

Nu

mb

er o

f G

rou

ps

Best Solutions

• Eric Park, Brian Tran, Joakim Arfvidsson– 3354 error pixels / score 84.3

• Fraser Cameron, Peter Kimball, Mike Vitus– 3447 error pixels / score 77.2

• Simon Berring, Anya Petrovskaya, Daniel Tarlow– 4337 error pixels / score 86.7

• Antoine el Daher– 4518 error pixels / score 87.2

Eric Park, Brian Tran, Joakim Arfvidsson

• Road detection:– sample road color from just in front of car– flood-fill the road using the sampled color– use the RANSAC to find the edges of the road– blur and threshold image

• Car edges detection:– Canny– normalize edges – extract horizontal and vertical edges from this result– apply pattern matching

• Use perspective to dismiss false positives

Eric Park, Brian Tran, Joakim Arfvidsson

Eric Park, Brian Tran, Joakim Arfvidsson

Eric Park, Brian Tran, Joakim Arfvidsson

Fraser Cameron, Peter Kimball, Mike Vitus

• Road finder– Prewitt edge convolution and a Hough Transform

• Tail light finder– based on color

• Shadow finder– looks for dark horizontal edges

• Box finder– uses data from the above to generate bounding box

• Pixel classifier– corner finding -> convex hull to trace car edges

Fraser Cameron, Peter Kimball, Mike Vitus

Road Finder

Taillight Finder

Fraser Cameron, Peter Kimball, Mike Vitus

Shadow Finder

Box Finder

Pixel Classifier

Simon Berring, Anya Petrovskaya, Daniel Tarlow

• Ran four classifiers and combined the results using a naive Bayes model:

1. boosted Haar classifier detector

2. color segmentation

3. corner finding

4. road finding

Simon Berring, Anya Petrovskaya, Daniel Tarlow

Haar Detector

Color Segmentation

CornerFinding

NaïveBayesModel

Antoine el Daher

• Trained several different boosted Haar classifiers:– 2 rear detectors– 1 "far away car" detector– 1 “side cars" detector– 1 "tail light" detector

• Ran a consistency checking phase– Make sure car is in road region at a plausible depth,

eliminate double detections• Ran a refinement phase

– Tighten bounding box around car using "cube" model of car

Antoine El Daher

Antoine El Daher

Taillight Mask

Road Detector

End Result